© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31376
    Prev
    Next
    INDEX
    Explanations

    former usage or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crowded
    -0.10
     queued
    -0.09
     landsc
    -0.08
     fro
    -0.08
     Walls
    -0.08
     glossy
    -0.08
     sticker
    -0.08
     skies
    -0.08
    opl
    -0.08
     Rune
    -0.08
    POSITIVE LOGITS
     abandoned
    0.34
     former
    0.26
     old
    0.24
     unused
    0.23
     abandon
    0.21
     formerly
    0.21
     Former
    0.21
     converted
    0.19
    former
    0.19
     discarded
    0.18
    Activations Density 0.469%

    No Known Activations